Skip to content

Commit 9a3b986

Browse files
Fix TRT-LLM 2-gpu CI test shm issue (#744)
- As suggested by NVGHA runners team to increase SHM size to avoid issue on 2-gpu nightly tests Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
1 parent 81c509c commit 9a3b986

2 files changed

Lines changed: 2 additions & 1 deletion

File tree

.github/workflows/_example_tests_runner.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -34,6 +34,7 @@ jobs:
3434
timeout-minutes: ${{ inputs.timeout_minutes }}
3535
container:
3636
image: ${{ inputs.docker_image }}
37+
options: --shm-size=2gb # TRT-LLM tests on 2-GPU runner needs more shared memory
3738
env:
3839
PIP_CONSTRAINT: "" # Disable pip constraint for upgrading packages
3940
HF_TOKEN: ${{ secrets.HF_TOKEN }}

.github/workflows/example_tests.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -93,7 +93,7 @@ jobs:
9393
strategy:
9494
fail-fast: false
9595
matrix:
96-
example: [llm_ptq] # vlm_ptq temporarily disabled due to pipeline error
96+
example: [llm_ptq] # vlm_ptq temporarily disabled due to pipeline error
9797
uses: ./.github/workflows/_example_tests_runner.yml
9898
secrets: inherit
9999
with:

0 commit comments

Comments
 (0)